Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond annotations (readOnly, idempotent), the description adds 'Execution: synchronous', 'Task support: forbidden', and states the returned JSON is internal application state for orchestration. It also provides response handling guidance (use assistantSummary, avoid raw JSON). This adds useful behavioral context beyond what annotations declare.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The first sentence is clear, but the description then becomes a run-on list of operational instructions (classification, execution, task support, response formatting) that repeats annotation info. Several sentences about never displaying raw JSON and using assistantSummary are about user interaction, not the tool's behavior, making it overlong.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Provides strong workflow context (when to use, read-only nature) but completely omits parameter details—especially options that control what assets are collected. With 7 parameters at 0% schema coverage and nested objects, the description is insufficient for an agent to know what values to pass. No mention of expected return structure despite an output schema existing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 0% description coverage and the description does not explain any of the 7 parameters, including required fields like advertiserId, brandName, websiteUrl. The collection goals are listed, but there is no mapping to options like maxLogos, fetchFonts, etc. Description fails to compensate for the lack of schema documentation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states the tool collects brand visual assets (logos, imagery, colours, fonts, previews) for Studio creative builds. The phrase 'Use this before build_ad' differentiates it from other getters in the workflow. Specific verb 'Collect' with a defined set of resources.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly directs use 'before build_ad when a campaign needs visual grounding' and notes it does not save to Studio, setting expectation of read-only usage. However, it does not name alternative tools like get_brand_profile or refresh_brand_visuals, so it scores below the highest tier.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.